Search

Abstract The coronary angiogram is the gold standard for evaluating the severity of coronary artery disease stenoses. Presently, the assessment is conducted visually by cardiologists, a method that lacks standardization. This study introduces DeepCoro, a ground-breaking AI-driven pipeline that integrates advanced vessel tracking and a video-based Swin3D model that was trained and validated on a dataset comprised of 182,418 coronary angiography videos spanning 5 years. DeepCoro achieved a notable precision of 71.89% in identifying coronary artery segments and demonstrated a mean absolute error of 20.15% (95% CI: 19.88–20.40) and a classification AUROC of 0.8294 (95% CI: 0.8215–0.8373) in stenosis percentage prediction compared to traditional cardiologist assessments. When compared to two expert interventional cardiologists, DeepCoro achieved lower variability than the clinical reports (19.09%; 95% CI: 18.55–19.58 vs 21.00%; 95% CI: 20.20–21.76, respectively). In addition, DeepCoro can be fine-tuned to a different modality type. When fine-tuned on quantitative coronary angiography assessments, DeepCoro attained an even lower mean absolute error of 7.75% (95% CI: 7.37–8.07), underscoring the reduced variability inherent to this method. This study establishes DeepCoro as an innovative video-based, adaptable tool in coronary artery disease analysis, significantly enhancing the precision and reliability of stenosis assessment.

Abstract Background Finding a noninvasive radiomic surrogate of tumor immune features could help identify patients more likely to respond to novel immune checkpoint inhibitors. Particularly, CD73 is an ectonucleotidase that catalyzes the breakdown of extracellular AMP into immunosuppressive adenosine, which can be blocked by therapeutic antibodies. High CD73 expression in colorectal cancer liver metastasis (CRLM) resected with curative intent is associated with early recurrence and shorter patient survival. The aim of this study was hence to evaluate whether machine learning analysis of preoperative liver CT-scan could estimate high vs low CD73 expression in CRLM and whether such radiomic score would have a prognostic significance. Methods We trained an Attentive Interpretable Tabular Learning (TabNet) model to predict, from preoperative CT images, stratified expression levels of CD73 (CD73High vs. CD73Low) assessed by immunofluorescence (IF) on tissue microarrays. Radiomic features were extracted from 160 segmented CRLM of 122 patients with matched IF data, preprocessed and used to train the predictive model. We applied a five-fold cross-validation and validated the performance on a hold-out test set. Results TabNet provided areas under the receiver operating characteristic curve of 0.95 (95% CI 0.87 to 1.0) and 0.79 (0.65 to 0.92) on the training and hold-out test sets respectively, and outperformed other machine learning models. The TabNet-derived score, termed rad-CD73, was positively correlated with CD73 histological expression in matched CRLM (Spearman’s ρ = 0.6004; P

Head and neck radiotherapy induces important toxicity, and its efficacy and tolerance vary widely across patients. Advancements in radiotherapy delivery techniques, along with the increased quality and frequency of image guidance, offer a unique opportunity to individualize radiotherapy based on imaging biomarkers, with the aim of improving radiation efficacy while reducing its toxicity. Various artificial intelligence models integrating clinical data and radiomics have shown encouraging results for toxicity and cancer control outcomes prediction in head and neck cancer radiotherapy. Clinical implementation of these models could lead to individualized risk-based therapeutic decision making, but the reliability of the current studies is limited. Understanding, validating and expanding these models to larger multi-institutional data sets and testing them in the context of clinical trials is needed to ensure safe clinical implementation. This review summarizes the current state of the art of machine learning models for prediction of head and neck cancer radiotherapy outcomes.

Abstract In radiation oncology, predicting patient risk stratification allows specialization of therapy intensification as well as selecting between systemic and regional treatments, all of which helps to improve patient outcome and quality of life. Deep learning offers an advantage over traditional radiomics for medical image processing by learning salient features from training data originating from multiple datasets. However, while their large capacity allows to combine high-level medical imaging data for outcome prediction, they lack generalization to be used across institutions. In this work, a pseudo-volumetric convolutional neural network with a deep preprocessor module and self-attention (PreSANet) is proposed for the prediction of distant metastasis, locoregional recurrence, and overall survival occurrence probabilities within the 10 year follow-up time frame for head and neck cancer patients with squamous cell carcinoma. The model is capable of processing multi-modal inputs of variable scan length, as well as integrating patient data in the prediction model. These proposed architectural features and additional modalities all serve to extract additional information from the available data when availability to additional samples is limited. This model was trained on the public Cancer Imaging Archive Head–Neck-PET–CT dataset consisting of 298 patients undergoing curative radio/chemo-radiotherapy and acquired from 4 different institutions. The model was further validated on an internal retrospective dataset with 371 patients acquired from one of the institutions in the training dataset. An extensive set of ablation experiments were performed to test the utility of the proposed model characteristics, achieving an AUROC of $$80\%$$ 80 % , $$80\%$$ 80 % and $$82\%$$ 82 % for DM, LR and OS respectively on the public TCIA Head–Neck-PET–CT dataset. External validation was performed on a retrospective dataset with 371 patients, achieving $$69\%$$ 69 % AUROC in all outcomes. To test for model generalization across sites, a validation scheme consisting of single site-holdout and cross-validation combining both datasets was used. The mean accuracy across 4 institutions obtained was $$72\%$$ 72 % , $$70\%$$ 70 % and $$71\%$$ 71 % for DM, LR and OS respectively. The proposed model demonstrates an effective method for tumor outcome prediction for multi-site, multi-modal combining both volumetric data and structured patient clinical data.

Background and purposeLocally recurrent prostate cancer after radiotherapy merits an effective salvage strategy that mitigates the risk of adverse events. We report outcomes of a cohort enrolled across two institutions investigating MRI-guided tumor-targeted salvage high dose rate brachytherapy (HDR-BT).Materials and methodsAnalysis of a prospective cohort of 88 patients treated across two institutions with MRI-guided salvage HDR-BT to visible local recurrence after radiotherapy (RT). Tumor target dose ranged from 22-26 Gy, using either an integrated boost (ibBT) or focal technique (fBT), delivered in two implants over a median of 7 days. Outcome metrics included cancer control and toxicity (CTCAE). Quality of life (QoL-EPIC) was analyzed in a subset.ResultsAt a median follow-up of 35 months (6 -134), 3 and 5-year failure-free survival (FFS) outcomes were 67% and 49%, respectively. At 5 years, fBT was associated with a 17% cumulative incidence of local failure (LF) outside the GTV (vs. 7.8% ibBT, p=0.14), while LF within the GTV occurred in 13% (vs. 16% ibBT, p=0.81). Predictors of LF outside fBT volumes included pre-salvage PSA>7 ng/mL (p=0.03) and interval since RT less than 5 years (p=0.04). No attributable grade 3 events occurred, and ibBT was associated with a higher rate of grade 2 toxicity (p

Macrocephaly is present in about 2–5% of the general population. It can be found as an isolated benign trait or as part of a syndromic condition. Brain overgrowth has been associated with neurodevelopmental disorders such as autism during the first year of life, however, evidence remains inconclusive. Furthermore, most of the studies have involved pathological or high-risk populations, but little is known about the effects of brain overgrowth on neurodevelopment in otherwise neurotypical infants. We investigated the impact of brain overgrowth on basic perceptual learning processes (repetition effects and change detection response) during the first year of life. We recorded high density electroencephalograms (EEG) in 116 full-term healthy infants aged between 3 and 11 months, 35 macrocephalic (14 girls) and 81 normocephalic (39 girls) classified according to the WHO head circumference norms. We used an adapted oddball paradigm, time-frequency analyses, and auditory event-related brain potentials (ERPs) to investigate differences between groups. We show that brain overgrowth has a significant impact on repetition effects and change detection response in the 10–20 Hz frequency band, and in N450 latency, suggesting that these correlates of sensorial learning processes are sensitive to brain overgrowth during the first year of life.

Abstract Interest for deep learning in radiology has increased tremendously in the past decade due to the high achievable performance for various computer vision tasks such as detection, segmentation, classification, monitoring, and prediction. This article provides step-by-step practical guidance for conducting a project that involves deep learning in radiology, from defining specifications, to deployment and scaling. Specifically, the objectives of this article are to provide an overview of clinical use cases of deep learning, describe the composition of multi-disciplinary team, and summarize current approaches to patient, data, model, and hardware selection. Key ideas will be illustrated by examples from a prototypical project on imaging of colorectal liver metastasis. This article illustrates the workflow for liver lesion detection, segmentation, classification, monitoring, and prediction of tumor recurrence and patient survival. Challenges are discussed, including ethical considerations, cohorting, data collection, anonymization, and availability of expert annotations. The practical guidance may be adapted to any project that requires automated medical image analysis.

Abstract Surgical guidance applications using Raman spectroscopy are being developed at a rapid pace in oncology to ensure safe and complete tumor resection during surgery. Clinical translation of these approaches relies on the acquisition of large spectral and histopathological data sets to train classification models. Data calibration must ensure compatibility across Raman systems and predictive model transferability to allow multi‐centric studies to be conducted. This paper addresses issues relating to Raman measurement standardization by first comparing Raman spectral measurements made on an optical phantom and acquired with nine distinct point probe systems and one wide‐field imaging instrument. Data standardization method led to normalized root‐mean‐square deviations between instruments of 2%. A classification model discriminating between white and gray matter was trained with one point probe system. When used to classify independent data sets acquired with the other systems, model predictions led to >95% accuracy, preliminarily demonstrating model transferability across different biomedical Raman spectroscopy instruments.

Magnetic resonance imaging (MRI) plays a critical role in the planning and monitoring of hepatocellular carcinomas (HCC) treated with locoregional therapies, in order to assess disease progression or recurrence. Dynamic contrast-enhanced (DCE)-MRI sequences offer temporal data on tumor enhancement characteristics which has strong prognostic value. Yet, predicting follow-up DCE-MR images from which tumor enhancement and viability can be measured, before treatment of HCC actually begins, remains an unsolved problem given the complexity of spatial and temporal information. We propose an approach to predict future DCE-MRI examinations following transarterial chemoembolization (TACE) by learning the spatio-temporal features related to HCC response from pre-TACE images. A novel Spatial-Temporal Discriminant Graph Neural Network (STDGNN) based on graph convolutional networks is presented. First, embeddings of viable, equivocal and non-viable HCCs are separated within a joint low-dimensional latent space, which is created using a discriminant neural network representing tumor-specific features. Spatial tumoral features from independent MRI volumes are then extracted with a structural branch, while dynamic features are extracted from the multi-phase sequence with a separate temporal branch. The model extracts spatio-temporal features by a joint minimization of the network branches. At testing, a pre-TACE diagnostic DCE-MRI is embedded on the discriminant spatio-temporal latent space, which is then translated to the follow-up domain space, thus allowing to predict the post-TACE DCE-MRI describing HCC treatment response. A dataset of 366 HCC’s from liver cancer patients was used to train and test the model using DCE-MRI examinations with associated pathological outcomes, with the spatio-temporal framework yielding 93.5% classification accuracy in response identification, and generating follow-up images yielding insignificant differences in perfusion parameters compared to ground-truth post-TACE examinations.

BACKGROUND:Prostate cancer (PC) is the most frequently diagnosed cancer in North American men. Pathologists are in critical need of accurate biomarkers to characterize PC, particularly to confirm the presence of intraductal carcinoma of the prostate (IDC-P), an aggressive histopathological variant for which therapeutic options are now available. Our aim was to identify IDC-P with Raman micro-spectroscopy (RμS) and machine learning technology following a protocol suitable for routine clinical histopathology laboratories. METHODS AND FINDINGS:We used RμS to differentiate IDC-P from PC, as well as PC and IDC-P from benign tissue on formalin-fixed paraffin-embedded first-line radical prostatectomy specimens (embedded in tissue microarrays [TMAs]) from 483 patients treated in 3 Canadian institutions between 1993 and 2013. The main measures were the presence or absence of IDC-P and of PC, regardless of the clinical outcomes. The median age at radical prostatectomy was 62 years. Most of the specimens from the first cohort (Centre hospitalier de l'Université de Montréal) were of Gleason score 3 + 3 = 6 (51%) while most of the specimens from the 2 other cohorts (University Health Network and Centre hospitalier universitaire de Québec-Université Laval) were of Gleason score 3 + 4 = 7 (51% and 52%, respectively). Most of the 483 patients were pT2 stage (44%-69%), and pT3a (22%-49%) was more frequent than pT3b (9%-12%). To investigate the prostate tissue of each patient, 2 consecutive sections of each TMA block were cut. The first section was transferred onto a glass slide to perform immunohistochemistry with H&E counterstaining for cell identification. The second section was placed on an aluminum slide, dewaxed, and then used to acquire an average of 7 Raman spectra per specimen (between 4 and 24 Raman spectra, 4 acquisitions/TMA core). Raman spectra of each cell type were then analyzed to retrieve tissue-specific molecular information and to generate classification models using machine learning technology. Models were trained and cross-validated using data from 1 institution. Accuracy, sensitivity, and specificity were 87% ± 5%, 86% ± 6%, and 89% ± 8%, respectively, to differentiate PC from benign tissue, and 95% ± 2%, 96% ± 4%, and 94% ± 2%, respectively, to differentiate IDC-P from PC. The trained models were then tested on Raman spectra from 2 independent institutions, reaching accuracies, sensitivities, and specificities of 84% and 86%, 84% and 87%, and 81% and 82%, respectively, to diagnose PC, and of 85% and 91%, 85% and 88%, and 86% and 93%, respectively, for the identification of IDC-P. IDC-P could further be differentiated from high-grade prostatic intraepithelial neoplasia (HGPIN), a pre-malignant intraductal proliferation that can be mistaken as IDC-P, with accuracies, sensitivities, and specificities > 95% in both training and testing cohorts. As we used stringent criteria to diagnose IDC-P, the main limitation of our study is the exclusion of borderline, difficult-to-classify lesions from our datasets. CONCLUSIONS:In this study, we developed classification models for the analysis of RμS data to differentiate IDC-P, PC, and benign tissue, including HGPIN. RμS could be a next-generation histopathological technique used to reinforce the identification of high-risk PC patients and lead to more precise diagnosis of IDC-P.

Abstract Objectives Liver volumetry has emerged as an important tool in clinical practice. Liver volume is assessed primarily via organ segmentation of computed tomography (CT) and magnetic resonance imaging (MRI) images. The goal of this paper is to provide an accessible overview of liver segmentation targeted at radiologists and other healthcare professionals. Methods Using images from CT and MRI, this paper reviews the indications for liver segmentation, technical approaches used in segmentation software and the developing roles of liver segmentation in clinical practice. Results Liver segmentation for volumetric assessment is indicated prior to major hepatectomy, portal vein embolisation, associating liver partition and portal vein ligation for staged hepatectomy (ALPPS) and transplant. Segmentation software can be categorised according to amount of user input involved: manual, semi-automated and fully automated. Manual segmentation is considered the “gold standard” in clinical practice and research, but is tedious and time-consuming. Increasingly automated segmentation approaches are more robust, but may suffer from certain segmentation pitfalls. Emerging applications of segmentation include surgical planning and integration with MRI-based biomarkers. Conclusions Liver segmentation has multiple clinical applications and is expanding in scope. Clinicians can employ semi-automated or fully automated segmentation options to more efficiently integrate volumetry into clinical practice. Teaching points • Liver volume is assessed via organ segmentation on CT and MRI examinations. • Liver segmentation is used for volume assessment prior to major hepatic procedures. • Segmentation approaches may be categorised according to the amount of user input involved. • Emerging applications include surgical planning and integration with MRI-based biomarkers.

Early identification of dementia in the early or late stages of mild cognitive impairment (MCI) is crucial for a timely diagnosis and slowing down the progression of Alzheimer’s disease (AD). Positron emission tomography (PET) is considered a highly powerful diagnostic biomarker, but few approaches investigated the efficacy of focusing on localized PET-active areas for classification purposes. In this work, we propose a pipeline using learned features from semantically labelled PET images to perform group classification. A deformable multimodal PET-MRI registration method is employed to fuse an annotated MNI template to each patient-specific PET scan, generating a fully labelled volume from which 10 common regions of interest used for AD diagnosis are extracted. The method was evaluated on 660 subjects from the ADNI database, yielding a classification accuracy of 91.2% for AD versus NC when using random forests combining features from cross-sectional and follow-up exams. A considerable improvement in the early versus late MCI classification accuracy was achieved using FDG-PET compared to the AV-45 compound, yielding a 72.5% rate. The pipeline demonstrates the potential of exploiting longitudinal multiregion PET features to improve cognitive assessment.